wangxiyuanandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> a4b14e57b6 [Platform] Allow BackendEnum dynamic register (#41091) ...

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-10-08 09:56:19 +08:00

..

attention

[Platform] Allow BackendEnum dynamic register (#41091)

2026-10-08 09:56:19 +08:00

core

[Bugfix][DSv4.1] Skip SWA bounded replay for KV loads that carry the window (#59197)

2026-10-07 15:28:42 -07:00

cudagraph

[Spec Decode] Rename AR speculators to StandaloneAR / TargetDependentAR (#60335)

2026-10-07 14:01:59 -04:00

determinism

[Kernel][LoRA] Add deterministic split-K=8 LoRA shrink for batch invariance (#59377)

2026-10-04 18:46:16 -04:00

distributed

[CI/Build] Warm the DP engines before measuring load balance in test_load (#60241)

2026-10-06 11:23:37 -05:00

e2e

[ROCm][CI] Add FP32 rounding slack to accuracy test near-tie upper bounds (#60292)

2026-10-07 08:19:22 -05:00

ec_connector

[EPD] Support metadata-only audio inputs (#57887)

2026-09-23 09:03:50 +08:00

engine

[Profiler] Add per-session profiling controls to Python and Rust frontends (#57875)

2026-10-06 05:21:19 +00:00

executor

[Core] Bound execute_dummy_batch RPC waits by the execute-model timeout (#60398)

2026-10-08 01:22:04 +00:00

fault_tolerance

[Feature] Add fault tolerance framework (simplified) for DP+EP external LB deployments (#44428)

2026-07-25 11:49:09 -04:00

kv_connector

[Bugfix][DSv4.1] Skip SWA bounded replay for KV loads that carry the window (#59197)

2026-10-07 15:28:42 -07:00

kv_offload

[Bugfix][KV Offload] Restore KVCR construction through the secondary-tier factory (#58088)

2026-10-07 21:36:57 +02:00

logits_processors

[MyPy][3/N] Fix MyPy errors in test groups (part 3) (#55939)

2026-09-30 11:06:07 +00:00

metrics

[Metrics] Expose cached prompt tokens by cache tier (#56318)

2026-10-06 14:52:05 -04:00

sample

[CI/Build] Widen the ragged prefill scoring tolerance, drop batch invariance (#60192)

2026-10-07 16:21:47 +08:00

shutdown

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

simple_kv_offload

[Metrics] Expose cached prompt tokens by cache tier (#56318)

2026-10-06 14:52:05 -04:00

spec_decode

[ModelRunner V2] Speculative Decoding NGram GPU Implementations (#40704)

2026-10-06 13:32:59 -07:00

streaming_input

[Bugfix][Core] Drop stale block hashes when a session truncates tokens (#59103)

2026-10-06 02:51:03 +00:00

structured_output

[Bugfix][Structured Output] Flag multi-branch allOf as unsupported for xgrammar (#59061)

2026-10-06 17:01:04 +04:00

tracing

[CI] Fix segfault in tracing test (#47299)

2026-07-01 14:00:37 +00:00

worker

[Spec Decode] Rename AR speculators to StandaloneAR / TargetDependentAR (#60335)

2026-10-07 14:01:59 -04:00

__init__.py

…

test_kv_cache_spec_registry.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

test_oracle.py

[Docs] Clean up speculators docs (#34065)

2026-02-18 13:48:11 -08:00

test_outputs.py

[Feature][Spec Decode] Support sampling mask replay for MRV2 MTP (#59359)

2026-10-01 13:51:39 +08:00

test_request.py

[Feature] Add first-class KV hints request envelope for programmatic KV management (#53423)

2026-09-21 09:56:11 -07:00

test_serial_utils.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_tensor_ipc_queue.py

[CI] Stabilize tensor IPC multiprocessing tests (#50804)

2026-08-12 10:16:43 +08:00

utils.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00